{"id":"https://openalex.org/W4283826357","doi":"https://doi.org/10.21437/interspeech.2022-10066","title":"Improving Transformer-based Conversational ASR by Inter-Sentential Attention Mechanism","display_name":"Improving Transformer-based Conversational ASR by Inter-Sentential Attention Mechanism","publication_year":2022,"publication_date":"2022-09-16","ids":{"openalex":"https://openalex.org/W4283826357","doi":"https://doi.org/10.21437/interspeech.2022-10066"},"language":"en","primary_location":{"id":"doi:10.21437/interspeech.2022-10066","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2022-10066","pdf_url":null,"source":{"id":"https://openalex.org/S4363604309","display_name":"Interspeech 2022","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2022","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":false,"oa_status":"closed","oa_url":null,"any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5100649112","display_name":"Kun Wei","orcid":null},"institutions":[{"id":"https://openalex.org/I17145004","display_name":"Northwestern Polytechnical University","ror":"https://ror.org/01y0j0j86","country_code":"CN","type":"education","lineage":["https://openalex.org/I17145004"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Kun Wei","raw_affiliation_strings":["Audio, Speech and Language Processing Group (ASLP@NPU), School of Computer Science, Northwestern Polytechnical University, Xian, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Audio, Speech and Language Processing Group (ASLP@NPU), School of Computer Science, Northwestern Polytechnical University, Xian, China","institution_ids":["https://openalex.org/I17145004"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101783173","display_name":"Pengcheng Guo","orcid":"https://orcid.org/0009-0001-2388-5935"},"institutions":[{"id":"https://openalex.org/I17145004","display_name":"Northwestern Polytechnical University","ror":"https://ror.org/01y0j0j86","country_code":"CN","type":"education","lineage":["https://openalex.org/I17145004"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Pengcheng Guo","raw_affiliation_strings":["Audio, Speech and Language Processing Group (ASLP@NPU), School of Computer Science, Northwestern Polytechnical University, Xian, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Audio, Speech and Language Processing Group (ASLP@NPU), School of Computer Science, Northwestern Polytechnical University, Xian, China","institution_ids":["https://openalex.org/I17145004"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5101443742","display_name":"Ning Jiang","orcid":"https://orcid.org/0000-0002-7152-3621"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Ning Jiang","raw_affiliation_strings":["Mashang Consumer Finance Co., Ltd"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Mashang Consumer Finance Co., Ltd","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":12,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"3804","last_page":"3808"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9980000257492065,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},"topics":[{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9980000257492065,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T10667","display_name":"Emotion and Mood Recognition","score":0.9961000084877014,"subfield":{"id":"https://openalex.org/subfields/3205","display_name":"Experimental and Cognitive Psychology"},"field":{"id":"https://openalex.org/fields/32","display_name":"Psychology"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},{"id":"https://openalex.org/T12031","display_name":"Speech and dialogue systems","score":0.9944999814033508,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7388816475868225},{"id":"https://openalex.org/keywords/transformer","display_name":"Transformer","score":0.7262678742408752},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.5199357867240906},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.5012919902801514},{"id":"https://openalex.org/keywords/mechanism","display_name":"Mechanism (biology)","score":0.44114723801612854},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3695685863494873},{"id":"https://openalex.org/keywords/electrical-engineering","display_name":"Electrical engineering","score":0.09028375148773193},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.0879763662815094},{"id":"https://openalex.org/keywords/physics","display_name":"Physics","score":0.07842817902565002},{"id":"https://openalex.org/keywords/voltage","display_name":"Voltage","score":0.05989733338356018}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7388816475868225},{"id":"https://openalex.org/C66322947","wikidata":"https://www.wikidata.org/wiki/Q11658","display_name":"Transformer","level":3,"score":0.7262678742408752},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.5199357867240906},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5012919902801514},{"id":"https://openalex.org/C89611455","wikidata":"https://www.wikidata.org/wiki/Q6804646","display_name":"Mechanism (biology)","level":2,"score":0.44114723801612854},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3695685863494873},{"id":"https://openalex.org/C119599485","wikidata":"https://www.wikidata.org/wiki/Q43035","display_name":"Electrical engineering","level":1,"score":0.09028375148773193},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.0879763662815094},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.07842817902565002},{"id":"https://openalex.org/C165801399","wikidata":"https://www.wikidata.org/wiki/Q25428","display_name":"Voltage","level":2,"score":0.05989733338356018},{"id":"https://openalex.org/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.21437/interspeech.2022-10066","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2022-10066","pdf_url":null,"source":{"id":"https://openalex.org/S4363604309","display_name":"Interspeech 2022","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2022","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4","score":0.46000000834465027}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":32,"referenced_works":["https://openalex.org/W179875071","https://openalex.org/W1524333225","https://openalex.org/W1526236009","https://openalex.org/W1999965501","https://openalex.org/W2091812280","https://openalex.org/W2166637769","https://openalex.org/W2197913429","https://openalex.org/W2573537087","https://openalex.org/W2597757402","https://openalex.org/W2886025712","https://openalex.org/W2891176389","https://openalex.org/W2892009249","https://openalex.org/W2912351236","https://openalex.org/W2936774411","https://openalex.org/W2937649809","https://openalex.org/W2962780374","https://openalex.org/W2963250244","https://openalex.org/W2963542740","https://openalex.org/W2964110616","https://openalex.org/W2972430654","https://openalex.org/W2972818416","https://openalex.org/W3007550212","https://openalex.org/W3015468748","https://openalex.org/W3096798607","https://openalex.org/W3097777922","https://openalex.org/W3144345593","https://openalex.org/W3163463193","https://openalex.org/W3163793923","https://openalex.org/W3176948526","https://openalex.org/W3177318507","https://openalex.org/W4288024261","https://openalex.org/W4385245566"],"related_works":["https://openalex.org/W2382997850","https://openalex.org/W2390968135","https://openalex.org/W2382213751","https://openalex.org/W2351750670","https://openalex.org/W1597848696","https://openalex.org/W2354715126","https://openalex.org/W2388563748","https://openalex.org/W2375179084","https://openalex.org/W2366646518","https://openalex.org/W3204019825"],"abstract_inverted_index":{"Transformer-based":[0,143],"models":[1],"have":[2],"demonstrated":[3],"their":[4],"effectiveness":[5,122],"in":[6,65],"automatic":[7],"speech":[8,73,85],"recognition":[9],"(ASR)":[10],"tasks":[11],"and":[12,86,132],"even":[13],"shown":[14],"superior":[15],"performance":[16,139],"over":[17],"the":[18,29,62,76,81,100,102,111,121,133,138,141],"conventional":[19],"hybrid":[20],"framework.The":[21],"main":[22],"idea":[23],"of":[24,83,104,123],"Transformers":[25],"is":[26,107],"to":[27,59],"capture":[28,80],"long-range":[30],"global":[31],"context":[32],"within":[33],"an":[34],"utterance":[35,106],"by":[36,94],"self-attention":[37],"layers.However,":[38],"for":[39,71,75],"scenarios":[40],"like":[41],"conversational":[42,72],"speech,":[43],"such":[44,88],"utterance-level":[45,142],"modeling":[46],"will":[47],"neglect":[48],"contextual":[49],"dependencies":[50],"that":[51],"span":[52],"across":[53],"utterances.In":[54],"this":[55],"paper,":[56],"we":[57,79],"propose":[58],"explicitly":[60],"model":[61],"inter-sentential":[63],"information":[64,90,114],"a":[66,95,116],"Transformer":[67],"based":[68],"end-to-end":[69],"architecture":[70],"recognition.Specifically,":[74],"encoder":[77],"network,":[78],"contexts":[82],"previous":[84],"incorporate":[87],"historic":[89,112],"into":[91],"current":[92,105],"input":[93],"context-aware":[96],"residual":[97],"attention":[98],"mechanism.For":[99],"decoder,":[101],"prediction":[103],"also":[108],"conditioned":[109],"on":[110,127],"linguistic":[113],"through":[115],"conditional":[117],"decoder":[118],"framework.We":[119],"show":[120],"our":[124],"proposed":[125,134],"method":[126,135],"several":[128],"open-source":[129],"dialogue":[130],"corpora":[131],"consistently":[136],"improved":[137],"from":[140],"ASR":[144],"models.":[145]},"counts_by_year":[{"year":2025,"cited_by_count":5},{"year":2024,"cited_by_count":4},{"year":2023,"cited_by_count":2},{"year":2022,"cited_by_count":1}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}